Jianzhu Guo

Jianzhu Guo
Chinese Academy of Sciences | CAS · National Laboratory of Pattern Recognition (NLPR), Institute of Automation

PhD Candicate

About

21
Publications
20,348
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
521
Citations
Citations since 2017
21 Research Items
521 Citations
2017201820192020202120222023050100150200
2017201820192020202120222023050100150200
2017201820192020202120222023050100150200
2017201820192020202120222023050100150200
Introduction
Jianzhu Guo currently works at the Automation Institute, Chinese Academy of Sciences. Jianzhu does research in Computer Vision, especially in Face Analysis and 3D face.

Publications

Publications (21)
Chapter
Full-text available
In the application of face recognition, eyeglasses could significantly degrade the recognition accuracy. A feasible method is to collect large-scale face images with eyeglasses for training deep learning methods. However, it is difficult to collect the images with and without glasses of the same identity, so that it is difficult to optimize the int...
Preprint
Full-text available
Face anti-spoofing is crucial for the security of face recognition systems. Learning based methods especially deep learning based methods need large-scale training samples to reduce overfitting. However, acquiring spoof data is very expensive since the live faces should be re-printed and re-captured in many views. In this paper, we present a method...
Chapter
Full-text available
Existing methods of 3D dthus limiting the scope of their practical applications. In this paper, we propose a novel regression framework which makes a balance among speed, accuracy and stability. Firstly, on the basis of a lightweight backbone, we propose a meta-joint optimization strategy to dynamically regress a small set of 3DMM parameters, which...
Article
Full-text available
Face recognition systems are sometimes deployed to a target domain with limited unlabeled samples available. For instance, a model trained on the large-scale webfaces maybe required to adapt to a NIR-VIS scenario via very limited unlabeled faces. This situation poses a great challenge to Unsupervised Domain Adaptation with Limited samples for Face...
Article
Unsupervised attribution graph embedding is challenging because structure and attribute information must be represented in the latent space. Existing reconstruction-based approaches optimize the latent space indirectly through decoders and thus may corrupt the manifold structure of the attributed graph and ultimately affect the performance of downs...
Article
A standard pipeline of current face recognition frameworks consists of four individual steps: locating a face with a rough bounding box and several fiducial landmarks, aligning the face image using a pre-defined template, extracting representations and comparing. Among them, face detection, landmark detection and representation learning have long b...
Preprint
Full-text available
Unsupervised attributed graph representation learning is challenging since both structural and feature information are required to be represented in the latent space. Existing methods concentrate on learning latent representation via reconstruction tasks, but cannot directly optimize representation and are prone to oversmoothing, thus limiting the...
Preprint
Full-text available
Mixup-based data augmentation has achieved great success as regularizer for deep neural networks. However, existing mixup methods require explicitly designed mixup policies. In this paper, we present a flexible, general Automatic Mixup (AutoMix) framework which utilizes discriminative features to learn a sample mixing policy adaptively. We regard m...
Preprint
Full-text available
A standard pipeline of current face recognition frameworks consists of four individual steps: locating a face with a rough bounding box and several fiducial landmarks, aligning the face image using a pre-defined template, extracting representations and comparing. Among them, face detection, landmark detection and representation learning have long b...
Chapter
Full-text available
Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency. However, most of their training data is constructed by 3D Morphable Model, whose space spanned is only a small part of the shape space. As a result, the reconstruction results lose the fine-grained geometry and look different fr...
Preprint
Full-text available
Existing methods of 3D dense face alignment mainly concentrate on accuracy, thus limiting the scope of their practical applications. In this paper, we propose a novel regression framework which makes a balance among speed, accuracy and stability. Firstly, on the basis of a lightweight backbone, we propose a meta-joint optimization strategy to dynam...
Preprint
Full-text available
Long-tailed problem has been an important topic in face recognition task. However, existing methods only concentrate on the long-tailed distribution of classes. Differently, we devote to the long-tailed domain distribution problem, which refers to the fact that a small number of domains frequently appear while other domains far less existing. The k...
Preprint
Full-text available
Face recognition systems are usually faced with unseen domains in real-world applications and show unsatisfactory performance due to their poor generalization. For example, a well-trained model on webface data cannot deal with the ID vs. Spot task in surveillance scenario. In this paper, we aim to learn a generalized model that can directly handle...
Preprint
Full-text available
Face anti-spoofing is crucial for the security of face recognition systems. Learning based methods especially deep learning based methods need large-scale training samples to reduce overfitting. However, acquiring spoof data is very expensive since the live faces should be reprinted and recaptured in many views. In this paper, we present a method t...
Preprint
Full-text available
In the application of face recognition, eyeglasses could significantly degrade the recognition accuracy. A feasible method is to collect large-scale face images with eyeglasses for training deep learning methods. However, it is difficult to collect the images with and without glasses of the same identity, so that it is difficult to optimize the int...
Article
Full-text available
Emotion recognition has a key role in affective computing. Recently, fine-grained emotion analysis, such as compound facial expression of emotions, has attracted high interest of researchers working on affective computing. A compound facial emotion includes dominant and complementary emotions (e.g. happily-disgusted, sadly-fearful), which is more d...
Article
Full-text available
Micro emotion recognition is a very challenging problem because of the subtle appearance variants among different facial expression classes. To deal with the mentioned problem, we proposed a multi-modality convolutional neural networks (CNNs) based on visual and geometrical information in this paper. The visual face image and structured geometry ar...

Network

Cited By

Projects

Projects (3)
Project
Research for vision